© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68733
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    えっ
    -1.08
    ごめん
    -1.06
    Dichloroethane
    -1.06
    あぁ
    -1.04
     году
    -1.01
    echy
    -0.99
    あー
    -0.98
     による
    -0.95
    Erreferentziak
    -0.94
    つづく
    -0.94
    POSITIVE LOGITS
    יהם
    1.03
    ﻣ
    1.00
     Beziehung
    0.98
    
    0.96
    ьере
    0.93
    但却
    0.93
    密的
    0.92
     at
    0.92
     inicios
    0.91
     instalaciones
    0.90
    Activations Density 0.003%

    No Known Activations